{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:21:15Z","timestamp":1783405275885,"version":"3.54.6"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Suicidal ideation (SI) in patients with major depressive disorder (MDD) is frequently underrecognized in early clinical assessment, owing to the complexity of its underlying neurobiological mechanisms and the lack of complementary objective biomarkers. To address this issue, this study proposes an interpretable deep learning framework designed to assist in the diagnosis of patients with MDD with suicidal ideation (MDDSI) and to elucidate its underlying neural mechanisms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A modified BrainNet convolutional neural network architecture was employed, utilizing a whole-brain functional connectivity (FC) matrix derived from resting-state functional magnetic resonance imaging as input features. A gradient-weighted class activation mapping algorithm was subsequently applied to visualize key brain regions. The study included 356 patients with MDDSI and 107 patients with MDD without suicidal ideation (MDDNSI) as the control group.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Five-fold cross-validation indicated that the model achieved an accuracy of 88%, sensitivity of 95%, specificity of 85%, and an area under the curve of 0.93 on the test set. Feature visualization results revealed that the model\u2019s classification decisions primarily relied on abnormal FC patterns in regions such as the motor cortex, anterior cingulate cortex, occipital lobe, temporal lobe, parietal lobe, and cerebellum.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This work provides a valuable reference for both auxiliary diagnosis and the mechanistic investigation of MDDSI.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fncom.2026.1821002","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T05:48:00Z","timestamp":1783403280000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable deep learning for functional MRI-based auxiliary diagnosis of major depressive disorder with suicidal ideation"],"prefix":"10.3389","volume":"20","author":[{"given":"Xiao","family":"Li","sequence":"first","affiliation":[{"name":"School of Medical Engineering, Henan Medical University","place":["Xinxiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Medical Engineering, Henan Medical University","place":["Xinxiang, China"]},{"name":"Xinxiang High Performance Computing Medical Engineering Technology Research Center","place":["Xinxiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinge","family":"Du","sequence":"additional","affiliation":[{"name":"School of Medical Engineering, Henan Medical University","place":["Xinxiang, China"]},{"name":"Xinxiang High Performance Computing Medical Engineering Technology Research Center","place":["Xinxiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoyong","family":"Guo","sequence":"additional","affiliation":[{"name":"Xinxiang High Performance Computing Medical Engineering Technology Research Center","place":["Xinxiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junfeng","family":"Ma","sequence":"additional","affiliation":[{"name":"Xinxiang High Performance Computing Medical Engineering Technology Research Center","place":["Xinxiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Medical Engineering, Henan Medical University","place":["Xinxiang, China"]},{"name":"Xinxiang High Performance Computing Medical Engineering Technology Research Center","place":["Xinxiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"8121","DOI":"10.3390\/ijerph17218121","article-title":"Major depressive disorder and suicide: a review of the literature","volume":"17","author":"Borentain","year":"2020","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"690130","DOI":"10.3389\/fpsyt.2021.690130","article-title":"Prevalence of suicidality in major depressive disorder: a systematic review and meta-analysis of comparative studies","volume":"12","author":"Cai","year":"2021","journal-title":"Front. Psych."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1016\/j.jad.2024.03.161","article-title":"Static and dynamic functional connectivity of the habenula in late-life depression patient with suicidal ideation","volume":"356","author":"Chen","year":"2024","journal-title":"J. Affect. Disord."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1109\/TMI.2022.3218745","article-title":"BrainGB: a benchmark for brain network analysis with graph neural networks","volume":"42","author":"Cui","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"111336","DOI":"10.1016\/j.brainresbull.2025.111336","article-title":"Exploring neural changes associated with suicidal ideation and attempts in major depressive disorder: a multimodal study","volume":"225","author":"Deng","year":"2025","journal-title":"Brain Res. Bull."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1083244","DOI":"10.3389\/fpsyt.2023.1083244","article-title":"Neuroimaging alterations of the suicidal brain and its relevance to practice: an updated review of MRI studies","volume":"14","author":"Dobbertin","year":"2023","journal-title":"Front. Psych."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1038\/s44220-022-00007-7","article-title":"Multimodal brain connectome-based prediction of suicide risk in people with late-life depression","volume":"1","author":"Gao","year":"2023","journal-title":"Nat. Ment. Health"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"665","DOI":"10.2147\/ndt.s238286","article-title":"Identifying suicidal ideation among Chinese patients with major depressive disorder: evidence from a real-world hospital-based study in China","volume":"16","author":"Ge","year":"2020","journal-title":"Neuropsychiatr. Dis. Treat."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"0659","DOI":"10.34133\/research.0659","article-title":"Transcriptional patterns of nodal entropy abnormalities in major depressive disorder patients with and without suicidal ideation","volume":"8","author":"Guo","year":"2025","journal-title":"Research"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1016\/j.neuroimage.2016.09.046","article-title":"BrainNetCNN: convolutional neural networks for brain networks; towards predicting neurodevelopment","volume":"146","author":"Kawahara","year":"2017","journal-title":"NeuroImage"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"9062022","DOI":"10.1155\/da\/9062022","article-title":"Characterizing psychiatric disorders through graph neural networks: a functional connectivity analysis of depression and schizophrenia","volume":"2025","author":"Lee","year":"2025","journal-title":"Depress. Anxiety"},{"key":"ref9002","first-page":"2406.07843v3","article-title":"Self-Attention-Based Contextual Modulation Improves Neural System Identification","author":"Lin","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.jpsychires.2019.08.002","article-title":"Changes in the global burden of depression from 1990 to 2017: findings from the global burden of disease study","volume":"126","author":"Liu","year":"2020","journal-title":"J. Psychiatr. Res."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"937145","DOI":"10.3389\/fnins.2022.937145","article-title":"Aberrant dynamic functional connectivity of posterior cingulate cortex subregions in major depressive disorder with suicidal ideation [original research]","volume":"16","author":"Li","year":"2022","journal-title":"Front. Neurosci."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1146\/annurev-clinpsy-072220-021440","article-title":"Major depression and its recurrences: life course matters","volume":"18","author":"Monroe","year":"2022","journal-title":"Annu. Rev. Clin. Psychol."},{"key":"ref9001","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1097\/CHI.0b013e318196b944","article-title":"Suicidal behavior among adolescents: correlates, confounds, and (the search for) causal mechanisms","volume":"48","author":"Nock","year":"2009","journal-title":"J. Am. Acad. Child Adolesc. Psychiatry."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1097\/yco.0b013e3280106868","article-title":"Suicide risk in mood disorders","volume":"20","author":"Rihmer","year":"2007","journal-title":"Curr. Opin. Psychiatry"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1006\/nimg.2001.0978","article-title":"Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain","volume":"15","author":"Tzourio-Mazoyer","year":"2002","journal-title":"NeuroImage"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1016\/j.jad.2024.10.009","article-title":"Alterations in orbitofrontal cortex communication relate to suicidal attempts in patients with major depressive disorder","volume":"369","author":"Wen","year":"2025","journal-title":"J. Affect. Disord."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1016\/s0140-6736(13)61611-6","article-title":"Global burden of disease attributable to mental and substance use disorders: findings from the global burden of disease study 2010","volume":"382","author":"Whiteford","year":"2013","journal-title":"Lancet"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1001\/archpsyc.1988.01800320058007","article-title":"A structured interview guide for the Hamilton depression rating scale","volume":"45","author":"Williams","year":"1988","journal-title":"Arch. Gen. Psychiatry"},{"key":"ref21","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e68910","DOI":"10.1371\/journal.pone.0068910","article-title":"BrainNet viewer: a network visualization tool for human brain connectomics","volume":"8","author":"Xia","year":"2013","journal-title":"PLoS One"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1038\/s41398-022-02147-x","article-title":"Identification of suicidality in patients with major depressive disorder via dynamic functional network connectivity signatures and machine learning","volume":"12","author":"Xu","year":"2022","journal-title":"Transl. Psychiatry"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"13","DOI":"10.3389\/fnsys.2010.00013","article-title":"DPARSF: a MATLAB toolbox for \u201cpipeline\u201d data analysis of resting-state fMRI","volume":"4","author":"Yan","year":"2010","journal-title":"Front. Syst. Neurosci."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"9078","DOI":"10.1073\/pnas.1900390116","article-title":"Reduced default mode network functional connectivity in patients with recurrent major depressive disorder","volume":"116","author":"Yan","year":"2019","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/j.jpsychires.2022.02.003","article-title":"Aberrant integrity of the cortico-limbic-striatal circuit in major depressive disorder with suicidal ideation","volume":"148","author":"Yang","year":"2022","journal-title":"J. Psychiatr. Res."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1491042","DOI":"10.3389\/fpsyt.2024.1491042","article-title":"Functional connectivity density of different suicidal behaviors in adolescents with major depressive disorders","volume":"15","author":"Zhong","year":"2024","journal-title":"Front. Psych."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1515\/revneuro-2024-0088","article-title":"Transformer-based approaches for neuroimaging: an in-depth review of their role in classification and regression tasks","volume":"36","author":"Zhu","year":"2025","journal-title":"Rev. Neurosci."}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2026.1821002\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T05:48:00Z","timestamp":1783403280000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2026.1821002\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,7]]},"references-count":30,"alternative-id":["10.3389\/fncom.2026.1821002"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2026.1821002","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,7]]},"article-number":"1821002"}}